Abstract
Self-supervised learning for image denoising problems in the presence of denaturation for noisy data is a crucial approach in machine learning. However, theoretical understanding of the performance of the approach that uses denatured data is lacking. To provide better understanding of the approach, in this paper, we analyze a self-supervised denoising algorithm that uses denatured data in depth through theoretical analysis and numerical experiments. Through the theoretical analysis, we discuss that the algorithm finds desired solutions to the optimization problem with the population risk, while the guarantee for the empirical risk depends on the hardness of the denoising task in terms of denaturation levels. We also conduct several experiments to investigate the performance of an extended algorithm in practice. The results indicate that the algorithm training with denatured images works, and the empirical performance aligns with the theoretical results. These results suggest several insights for further improvement of self-supervised image denoising that uses denatured data in future directions.
Abstract (translated)
自我监督学习在噪声数据中进行图像去噪问题是机器学习中的一个关键方法。然而,对于使用去噪数据的开源算法的性能理解还存在理论上的不足。为了更好地理解这种方法,本文分析了一种使用去噪数据的深度自我监督去噪算法,并通过理论分析和数值实验进行了分析。通过理论分析,我们讨论了该算法在优化问题中找到所需解的问题,而保证经验风险的保证取决于去噪任务的复杂程度。我们还进行了一些实验,研究了使用去噪图像进行训练的扩展算法的实际效果。结果表明,该算法基于去噪图像的训练是有效的,而经验性能与理论结果一致。这些结果为未来使用去噪数据进行图像去噪的自我监督学习提供了几个有价值的启示。
URL
https://arxiv.org/abs/2405.01124